Examinando por Autor "González Veloza, José John Fredy"
Mostrando 1 - 20 de 39
Resultados por página
Opciones de ordenación
- ÍtemAnálisis de modelo MA(1). Caso de estudio: Recaudo en una entidad financieraMedellin Valbuena, Laura Marcela; González Veloza, José John FredySome financial entities generally must meet a series of loans to their customers. For this, these entities must have a correct planning of the cash that should be available without exceeding your quotas. For this, financial entities carry out a hiring people specialized in cash projection, these people are in charge of to know when more money should be injected into office vaults or when more money should be collect money and keep even your funds in the securities carriers. Many internal factors intervene in the daily planning exercise of each office and external, several of these difficult to predict, such as the commercial strength of each office, the weather, the country's economy, among others
- ÍtemAnálisis de riesgo de cartera a través de machine learning para predecir la propensión de incumplimiento en seguros(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Hernandez Solano, Carolina; González Veloza, José John FredyInsurers in Colombia obtain their income from the monthly premiums paid by their clients and this article analyzed a database of an insurance company that offers an individual life insurance product with a savings component; To improve the portfolio risk indicators, the cancellation of policies and increase income, a model was made to predict the propensity for non-compliance in the payment of monthly premiums. To achieve this objective, several models were compared, having a rule-based model as a reference point and the other models were made through the machine learning methodology, identifying the Linear Discriminant Analysis model as the best, obtaining a recall result. of 0.58% and identifying the characteristics or variables of each client that are directly related to default and thereby predict whether new clients will default; thus, proposing to the company tools that allow decision making and/or define new marketing strategies.
- ÍtemAnálisis de Siniestralidad Peatonal A partir de la metodología de Machine Learning(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Martínez Ramos, Magda Milena; Vásquez López, Leidy Johana; González Veloza, José John FredyIntroduction The pedestrian accident rate is studied, being one of the leading causes of death in the world, a fact for which the World Health Organization called it a pandemic in its reports (World Health Organization (OMS)), this study It is carried out from the Machine Learning methodology. General Objective: Predict if a pedestrian in a sinister road is killed or injured. Results: Oversampling was used for the training data, where a confusion matrix was obtained, which adequately predicts the injured with an Precision, accuracy and reliability of 90%, while it is only capable of predicting half of the dead.
- ÍtemAnálisis estadístico para la predicción de la probabilidad de encontrar adultos mayores desaparecidos mediante la aplicación de modelos de aprendizaje automático(Fundación Universitaria Los Libertadores. Sede Bogotá., ) González Veloza, José John Fredy; Romero Ospina, Manuel FranciscoThe disappearance of persons is an enigmatic and frequent phenomenon that can have negative consequences for the disappeared person, their family and society in general. Age-related cognitive changes and increased vulnerability to dementia may increase the propensity of older adults to fade. The present study sought to identify individual and environmental factors that could predict whether an older adult reported missing would be found. Supervised machine learning models based on the open data of cases of disappeared persons from Colombia between 1930 and June 2021 (n = 7,855) were used. Classification algorithms were trained to predict whether a missing older adult would eventually be found. The best performing classification models in the test data were: Gradient Boosting Classifier and Light Gradient Boosting Machine, which showed, respectively, 10% and 9% more AUC than a reference model based on the average of elapsed time. since the disappearance. The features that most contributed to the classification were: the time elapsed since the disappearance, the place where it occurred, the age and sex of the disappeared person. The present results shed light on the social phenomenon of missing persons and lay the groundwork for the application of machine learning models in cases of missing older persons.
- ÍtemCaracterización de la autopercepción de los docentes de ciencias y matemáticas sobre el desarrollo de sus competencias científicas.Cárdenas Delgado, Oscar Oswaldo; González Veloza, José John Fredy; Fonseca Gómez, Lida RubielaCurrent research on science teaching focuses on the competencies of teachers for teaching in secondary and basic education in a technological and social context. In this research we explored the perception of science and mathematics teachers in the city of Manizales, around their own conceptions of scientific competencies in science teaching. A test was developed in Likert scale from 1 to 7, by means of which we carried out this investigation. This test was validated with Cronbach's alpha (0.99). Later, the answers of the instrument were analyzed with the free software R, using the quantitative methods exploratory and confirmatory factorial analysis. Three factors associated to practice and scientific research were detected, which constitute the indicators to characterize the perceptions of science teachers in Manizales, about their scientific competences for teaching.
- ÍtemClasificación de variables que representan mayor impacto al incumplirse al momento de otorgar cartera de microcréditos(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Herrera Carranza, Gamaliel; González Veloza, José John FredyThe granting of credit products in the Colombian financial market, specifically in the microcredit lines, implies a higher level of risk, taking into account the nature of the profile of the clients to whom these products are granted, who are mostly people with high levels of vulnerability, little or minimal credit experience and marked informality in the development of their economic activities, therefore It is important to identify which credit policies are more relevant when the client deteriorates or does not pay timely the value of the installments corresponding to the disbursed credits. That is why it is considered pertinent to carry out an analysis of the variables (credit policies) that are evaluated during the analysis process and approval of credit applications, since it has been identified that those customers who have incurred in arrears, did not initially comply with any of the credit policies that should be considered for approval of credit. So, according to the results of the analysis, it is considered important to integrate into the methodology evaluation, analysis and granting, some adjustments to the level of demand in compliance with the policies that generate a greater impact or possibly explain non-payment by customers, such as example: control the amount of the disbursement, exclude or request greater guarantees from clients who carry out activities companies that showed a bad payment habit, with which they can improve their portfolio quality indicators.
- ÍtemClasificación litológica a partir de registros eléctricos utilizando machine learning: caso de estudio formación otaraoa, Nueva Zelanda.(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Martínez Bernal, Margarita María; González Veloza, José John FredyIn the oil industry, when exploration well drilling, the uncertainty is excessively high since it is necessary to determine the characteristics of the subsurface and thus the possibilities that oil or gas exists. Indirect methods such as well logs are what provide the basis for geological investigation studies (sedimentary facies, groundwater) which is a complex activity that requires time but allows the evaluator to make decisions. By applying an automatic learning model, we want to reduce this uncertainty and minimize the time in the analysis of well logs. In this study, lithology prediction is investigated using electrical logs (Gamma Rays, Neutron, Density and Photoelectric Effect (PEF)) taken at the Fm. Otaraoa in New Zealand. The training of a Supervised model is carried out where two problems are addressed: the first of identification of two labels (Sand and Clay) and the second of four labels (Sandy Clay, Calcareous Sandy Clay, Clayey Sand and Calcareous Clayey Sand). One well is used to train an algorithm for each case and then two complementary wells are used to test its performance. The results of the Extra Trees Classifier model show that for Problem 1 an Accuracy of 93% was obtained, exceeding the metrics of the model based on rules (Accuracy of 87%), while in Problem 2 the Accuracy was 86%. The model in Problem 1 will learn to recognize the lithology pre-established by the human expert and for Problem 2 it is important to continue feeding the model training with more data from other wells or with core descriptions.
- ÍtemDiseño de un modelo de aprendizaje automático para la predicción de casos de infección por SARS-CoV-2 a partir de parámetros clínicos de laboratorio(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Prada Robles, Diana Carolina; González Veloza, José John FredyThe diagnosis of COVID-19 is crucial for the identification, isolation and treatment of contagious individuals, in order to mitigate the increase in cases as much as possible, and classify and prioritize them, according to the complexity of the disease manifestation. Although there are highly sensitive diagnostic tests, not all health institutions have the infrastructure or technology to perform them, consequently, the process must be outsourced, lengthening the diagnosis itself. Therefore, the present study focuses on design a machine learning model that allows predict cases of SARS-CoV-2 infection from clinical laboratory parameters, in the hospitalization service of a health institution in eastern of Colombia. Methodology: With the data of some biomarkers from the clinical laboratory, those that had a significant association with the spread of SARS-CoV-2 were evaluated, developing different machine learning algorithms, using PYTHON language libraries. Results: The Random Forest classifier was obtained as the best model with an AUCROC of 0.79, a sensitivity of 78% and an accuracy of 72%. Conclusion: The use of some blood biomarkers linked with machine learning algorithms can be useful tools for the prognosis of many diseases, including COVID-19.
- ÍtemFactores de predicción de la aparición de personas mayores reportadas como desaparecidas, a partir de modelos de aprendizaje automático supervisado(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Ruiz Rizzo, Adriana Lucía; González Veloza, José John FredyPerson missingness is an enigmatic and frequent phenomenon that can bring about negative consequences for the missing person, their family, and society in general. Therefore, it is necessary to better understand the phenomenon of missingness and thus find ways to solve cases in the most adequate manner for all parties involved. Age-related cognitive changes and a higher vulnerability to dementia can increase the likelihood of older adults going missing. Thus, the present study sought to identify individual and environmental factors that might predict that an older adult reported missing will be found. To do so, supervised machine learning models were used based on the missing person cases open data of Colombia between 1930 and June, 2021 (n = 7855). Classification algorithms were trained to predict whether an older adult who went missing would eventually be found. The classification models with the best performance in the test data were those based on decision trees. Particularly, the Light Gradient Boosting Machine algorithm showed 71% classification accuracy (i.e., 8% above a base model built with the mean of the reported missingness period of the training data). The features with the greatest contribution to the classification were date and place of the missing person case, as well as the age and sex of the missing person. These results help us better understand the societal phenomenon of person missingness and can have important practical implications.
- ÍtemFactores de predicción para la detección temprana de trastornos neurocognitivos en personas institucionalizadas en centros de protección social pertenecientes a la beneficencia de Cundinamarca(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Parada Hernández, Andrés; González Veloza, José John FredyNeurocognitive disorders are increasing significantly in the elderly population. elderly population. From this point of view, it is important to understand this phenomenon as the result of a multiplicity of variables as the result of a multiplicity of variables in which the social context and intellectual impairment and intellectual impairment establish elements of study in line with the identification of risk and/or contributory factors. risk and/or contributory factors. Individuals with intellectual developmental disorder with mild impairment are more likely to be with mild impairment are more likely to acquire a specific type of dementia, which generally begins to show early signs of dementia, which usually begins to show early signs. The present study aimed to identify potential cases in people institutionalized in Social Protection Centers of the Beneficencia de Cundinamarca. of the Beneficencia de Cundinamarca in order to establish early therapeutic actions to control the to control mental deterioration and the costs associated with the treatments. The study took into account 32 predictor variables obtained through the Wechsler Scale of Intelligence. Wechsler Adult Intelligence Scale and Mini-Mental State Examination. Based on the analysis of existing data in the Social Protection Centers of the Beneficencia de Cundinamarca in 2018, in Cundinamarca in 2018, 2020 and 2022 (n = 294), statistical models were trained which divided the objective variable: diagnosis of dementia in 2022 into independent components oriented to the oriented to the prediction of potential cases according to the prevalence of some type of according to the prevalence of some type of impairment. Once the data were processed, the classification model that performed best was the Random classification model that presented the best performance was the Random Forest Classifier, yielding a 2 AUC of 0.97, 0.01 higher than the Light Gradient Boosting Machine, and 0.1 higher than the Logisctic Regression initially proposed. The variables that best contributed to the prediction were related to the evocative memory were related to evocative memory, temporal organization, immediate memory, attention and calculation, baseline diagnosis, executive quotient and age.
- ÍtemFactores que predicen la culminación de la formación a nivel de pregrado a partir de la prueba Saber 11 y el cuestionario socioeconómico(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Bonilla Naranjo, María Fernanda; González Veloza, José John FredyThis study aims to identify the socioeconomic factors that predict the factors associated with the education gap in Colombia. associated with the educational gap in Colombia. The results of the socioeconomic questionnaire and the questionnaire and the Saber 11 tests reported by the Institute for the Evaluation of Education (ICFES) from 2012-1 to 2016-2 Education (ICFES) from the periods 2012-1 to 2016-2, and as a response variable, having taken the Saber Pro exam (under the the Saber Pro exam (under the hypothesis that taking it is an indicator of having completed their university studies and not taking it, on the contrary, assumes the fact of not having had access to or having dropped out of this educational process. having dropped out of this formative process). Supervised automatic learning techniques were used, implementing the techniques were used, implementing the Light Gradient Boosting Machine model for the analysis of the information. information. As the main results, it was identified that the main sociodemographic variables related to the fact sociodemographic variables related to the fact of finishing or completing the formative process at the undergraduate level were at the undergraduate level are: belonging to the female gender, having access to the Internet at home, studying in a full-time educational institution, and the mother's professional training; In addition, the variables that are the best predictors of NOT being in the process of completing higher education at the undergraduate level are the variables that are better predictors of NOT being in the process of completing higher education at the undergraduate level are related to low family income, residing in rural areas, and being in a rural area. family income, living in rural areas, and not having access to a computer at home.
- ÍtemIdentificación y pronóstico de sífilis congénita mediante técnicas de Aprendizaje Automático para las localidades de Usme, Tunjuelito, Ciudad Bolívar y Sumapaz (Bogotá D.C.)(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Macana González, Carlos Fernando; González Veloza, José John FredyCongenital syphilis is a serious bacterial infection transmitted in a newborn from a mother who was not treated or was inadequately treated for syphilis during pregnancy; the consequences of this infection in the baby are related to an affectation in the quality of life and diseases such as abdominal masses, low weight, skeletal abnormalities and bone pain, joint inflammation, blindness, deafness, among others, and even death, so it is a problem of interest in public health worldwide; This has led governments and scientists to search for strategies to reduce new cases of syphilis in infants; hence the importance of having predictive models as a tool for early identification of risk factors or variables in pregnant women and thus perform a health action to prevent the transmission of syphilis to the newborn. From this point of gravity and impact that congenital syphilis generates, the present work used machine learning techniques for the elaboration of predictive models that support the identification of variables related to the appearance of new cases of infected newborns and that are useful in health institutions for the timely management of treatment in pregnant women; this from the knowledge of sociodemographic and health variables of the mother and her context. A data set was available that compiles sociodemographic and health information of a cohort of 451 pregnant women with positive diagnosis for syphilis; basic information was available about the newborn in terms of weight and syphilis infection status; it was identified in the data set that 21.5% (n=97) of the births of mothers with syphilis were also born with syphilis (congenital syphilis); 12 prediction models of congenital syphilis were trained using supervised automatic learning techniques. The main result has been to generate four predictive models, K Neighbors Classifier, Light Gradient Boosting Machine, Gradient Boosting Classifier and Random Forest Classifier. The performance metrics of the predictive models were evaluated to select the best of them, achieving an F1-Score of 77.28% in the model based on K Neighbors Classifier, 73.69% in the model based on Light Gradient Boosting Machine, 73.76% in the model based on Gradient Boosting Classifier and 68.38% in the model based on Random Forest Classifier, also with sensitivity above 70%, exceeding the performance metrics of an initial model based on rules; are considered as relevant variables in the predictive potential of the model based on machine learning algorithms: the number of weeks of gestation at the time of the first prenatal checkup; the age of the mother and the; origin of the mother and the number of expected total prenatal checkups.
- ÍtemMachine learning para la segmentación y optimización de los costos de adquisición de clientes(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Forero González, Álvaro Antonio; González Veloza, José John FredyThis work develops an important advance in the classification, prediction and segmentation of Casur affiliates, as part of its strategic objectives, facilitating the entity's planning. To do this, basic rule models were adopted, followed by machine learning classification and clustering models. Of which the first were used as a basis for comparison and the last two were used as input in the rest of the analysis. However, since the models have associated errors, the binomial probability distribution model was used to find the number of commercial approaches necessary to have, at least, one sale with a probability of 99%; and optimize, in this way, the customer acquisition model, with which it was also possible to compare the best model, according to the current state of the entity.
- ÍtemMedición de material óptico en Bogotá con la técnica de espectrofotometría uv-vis dentro del estándar nist para temperatura y humedad(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Núñez Patiño, Andrés; González Veloza, José John FredyAnalysis of historical data of the temperature and humidity of the F'enix Technology and Development laboratory located in the city of Bogotá, this is accredited by ONAC (Colombian National Accreditation Body) to calibrate materials Spectrophotometry optics in the UV-VIS range. The analysis was performed using multivariate capability index statistical techniques, first performing an analysis of correlation between the variables of temperature and humidity. An analysis of the behavior of the two variables was carried out over the years of operation of the laboratory, Initially, all the collected data was made together, a purification was carried out of data and finally the changes made to regain control are analyzed. It was concluded that the laboratory can perform this type of measurement in the climate of the city Bogotá, taking into account the materials and the specific location of the laboratory; this will allow the laboratory and others that need to make this type of measurement in the city of Bogotá, improve operating conditions to meet standards international.
- ÍtemModelo de aprendizaje automático para riesgo crediticio de microempresarios regionales según perfil socioeconómico(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Betancur Londoño, Carlos Mario; González Veloza, José John FredyThe credit portfolio is fundamental in a financial entity, therefore, before each credit delivered, the hope is to recover it in times agreed with the client, even so, the risk of non payment during the term of the obligation is latent. The proposal of a prediction model with different techniques that defines the probability of default, can help define the possible socioeconomic causes that imply risk of default. The achievement of the defaults caused at the moment was taken with the objective of identifying clients that could incur in a state of default and risk of non-payment. The modeling was done in order to mitigate or filter the users to whom the credit is granted and helps us define how they can be classified as a potential default holder, this, determined by the profiles provided by the more than 39 thousand individuals that make up the database. The market niche to which the institution is directed is made up of users with limited economic scope to start their business or micro entrepreneurs who require working capital for their ongoing business, all of them with a common interest, to create a business and get ahead with your idea, regardless of academic levels, financial muscle or urban or rural residence. A solid concept of the project and its implementation is necessary. It is essential to be clear about the market niche to which the institution is directed, and for this reason it is important to consider what its profile is. The models exposed in this project have foundations of support for the area of credit studies or central financial evaluation. The modeling procedure was carried out with supervised machine learning methods such as logistic regression, random forest and gradient boosting. Three options of which the random forest was chosen as the best, according to its metrics. The comparison was made with the current credit evaluation methodology and the implications were determined in case of being implemented.
- ÍtemModelo de clasificación machine learning para pronosticar secuelas físicas en pacientes postcovid.(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Figueroa Arias, José Julián; González Veloza, José John FredyCovid 19 is an infectious virus that produces a severe acute respiratory syndrome, and among the most frequent symptoms are respiratory symptoms, fever and also gastrointestinal symptoms. One of the characteristics of this virus is that after the recovery period, in some cases there are physical sequelae such as coughing, loss of smell, muscle pain, headache, etc., sequelae that have caused fatalities throughout the world. Therefore, in this study, a machine learning classification model was carried out to predict physical sequelae in postcovid patients, as a sample, information was obtained from 1436 observations of patients from the Nariño Departmental University Hospital who were positive for covid 19, after recovery. Information was obtained from these patients on the variable of interest for this study, which was the presentation of post-COVID physical sequelae. It was found that the model with the best performance metrics was the classification tree with auc of 0.73. It is concluded that the classification model is useful to identify possible cases of individuals with post-covid sequelae and thus manage hospital actions to reduce complications and fatalities after the recovery period caused by the Covid-19 virus.
- ÍtemModelo de estimación de perfiles laborales exitosos. Caso de estudio: Entidad financiera(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Cifuentes Ruiz, Juan Camilo; Flórez Díaz, Jonathan Camilo; Valcárcel Gómez, Edgar Alejandro; González Veloza, José John FredyThe following work was carried out with the need to create a tool that would allow us to predict possible successful profiles. It was carried out by non-linear estimation methods with machine learning methods as logistics regressions or random forest. A model built that allowed us to be more objective when choosing a profile for the commercial strength of a certain bank. The results produced by the model show us a more objective way of choosing job profiles, as well as obtaining the variables that are significant when choosing the candidate.
- ÍtemModelo de pronóstico para estimar el comportamiento de ventas en pospago digital, de una empresa del sector telecomunicaciones en Colombia(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Arcos Fonseca, Edwin Fabian; González Veloza, José John FredyThe objective of this work is to propose a statistical model that allows forecasting the monthly sales of postpaid aircraft of a telecommunications company, this is due to the fact that in Colombia in the processes of activation of postpaid aircraft of the digital channel it has time dates of activation managed by the ABD (Data Base Administrator) that causes sales to be effective until approximately 5 business days before the end of the month, due to sim delivery and portability processes, this causes that if you do not have a good forecast at the The middle of the month is when alerts appear that show marketing cost overruns to be able to increase sales, the current model every month we have a gap of more than a thousand even reaching -4765, something that is not correct is annexed table 1. Table 1. Current projection gap. The current cost per discharge is approximately 41,500 and as we observe every month a negative GAP is being presented vs. the goal, there are projections with a lag greater than 2000 almost every month, which causes projected values to be showing close to the goal that there is some calm at the beginning of the month and approximately halfway through the alert is given that we are in the real below. Currently trying to recover what was lost generates an extra cost of almost double and just as from the beginning there is a budget and when a breach is generated it is money, for example in the month of October they stopped receiving $-135,539,000 that they should contribute the area for company goals, this in the future may cause more radical decisions for the area. To carry out the analysis, a comparison was made of the Holt-Winters and Arima models with these models, forecasts can be obtained to be able to make decisions, the data available is only that corresponding to January 2021, the complexity of the case is that As there is no comparison for more than one year, it is not possible to identify trends that occurred in the same month in previous years, in order to know if there are months in which a high or low behavior is normal, although in the same way the models developed allow us to know that sales they were not as high as expected and to be able to have a more timely reaction.
- ÍtemModelo de regresión para predecir el puntaje esperado en la Saber 11 para los estudiantes del colegio Cajasai(Fundación Universitaria Los Libertadores. Sede Bogotá., ) Cardozo Anaya, John Michael; González Veloza, José John FredyCurrently, students who aspire to be professionals have their hopes in the results they can obtain in the Saber 11 tests, because through these it is possible to aspire to obtain a scholarship, a condemnable credit or otherwise a place to be admitted to an institution of higher education. In the same way, educational institutions, when their students obtain high scores, allow them to obtain benefits such as accreditation with quality indexes, to be located in a better ranking and above all, prestige in the social environment. It is here where the purpose of constructing a regression model that allows to establish the future score that students of the island of San Andres belonging to the Cajasai School can obtain. Based on the data provided by an educational company (Edúcate) external to the school, corresponding to the results of the simulations carried out during the year 2022 and of the Saber 11 tests of the same year, several regression models were trained using supervised automated learning to predict the score of the students of San Andrés. The regression model with the highest performance on the test data was Huber with an RSME of 26.2683. The results obtained will make it possible to determine the score that a student can obtain when taking the Saber 11 test, based on the scores achieved in the simulations carried out by the consulting company.
- ÍtemModelo de scoring para crédito de consumo en una entidad del sector solidario(Fundación Universitaria Los Libertadores. Sede Bogotá., ) González Parga, Arbey; González Veloza, José John FredyIn Colombia, the Superintendence of the Solidarity Economy through the Basic Accounting Circular, Title IV, Chapter II regulates the SARC as the Credit Risk Management System that must be implemented and/or complemented by the supervised solidarity organizations, with the purpose of, identify, measure, control and monitor the credit risk to which they are exposed in the development of their granting process. Having said the above, it is necessary for the entities of the sector that place credits, to have their own models that obtain the most relevant variables and that allow the calculation of the probability of default based on the information of the credits that the entity has and to qualify accordingly. periodically each of the current credits. The main objective of this article is to explain how the most relevant variables can be obtained to calculate the probability of default of a client and create an internal score for new loans in order to support the granting decision through a machine learning model. This article was carried out using a database of a solidarity sector entity that contains a total of 5974 consumer loans and through automatic learning different models were trained to determine the probability of default of a client. The light gradient boosting machine model had the best performance with an AUC of 0.7550, recall of 0.7111, precision 0.1587. In addition, among the available variables, the ones that are most important to infer the probability of default for a consumer loan are age, total assets, total liabilities, monthly income, monthly expenses, credit value, term, level of study, status civil, form of payment and age.